Can I increase the L2 cache memory of my CPU?
I noticed that my laptop seems to have 4x the amount of "L2 cache memory" than my desktop, is that normal?
- laptop: Intel Core Duo CPU T2450 @ 2.00GHz, L2 cache memory 2 MB, system bus 533 MHz
- desktop: Intel Celeron D CPU 347 3.06GHz, bus 533 MHz, L2 cache memory 512 KB
Is there a way for me to increase the L2 cache memory on my desktop? Would it make the computer faster? I have 3 GB of RAM in it.
the L2 cache is built into the CPU itself. The only way to get more is to replace your CPU with one that has more L2 cache.
The Celeron is more of a budget class processor compared to your C2D, so it makes sense that it has less cache.
Will more cache be faster? In most cases, yes.
In the case of your desktop, depending on the socket you can replace the CPU with a new unit that not only has more cache, but with a faster clock speed as well.
This question is answered very clearly by NoCarrier
.
I am just adding a short reference that has a two sided use,
- Gives you a bit more breadth in the Cache theory
- useful for understanding newer architectures (Nehalem...)
- For all those memory performance power users on this site,
- gives you an idea of how caches work and which sizes matter when deciding your PC
Memory part 2: CPU caches at the LWN.net site (Oct, 2007).
Editor's note: This is the second installment in Ulrich Drepper's "What every programmer should know about memory" document. Those who have not read the first part will likely want to start there. This is good stuff, and we once again thank Ulrich for allowing us to publish it.
The longish article may also help understand why the caches were moved into the processor module (as against the old days described by cwrea
in the comment above, which are better forgotten).
Nehalem L3 cache note at ExtremeTech.
Update:
An old Overclocking article reference that I did not include earlier specifically because it does not apply to L2 Cache scaling. It is interesting to read in the context of my comments to another answer here (by hanleyp
).
From Three Gems for an Overclocker: on the Intel Celeron 2GHz,
Intel Celeron were always based on the same cores as the faster processor families, with that only difference that the L2 cache was twice as small, bus frequency was reduced and the clock frequencies were lower. As for the cache, there is no way to get its cut-down half back, however, in terms of frequencies, overclocking comes to rescue and allows speeding up the low-cost processors immensely. Not so long ago, following in the footsteps of Pentium 4, Celeron processor family acquired a 0.13micron Northwood core. The first Celeron CPUs based on it appeared Celeron 2.0GHz. As we have expected, they appeared very easy to overclock. Their core frequency can be raised up to that of the fastest Pentium 4 models, which is roughly 3GHz. And only the cut down 128KB L2 cache, prevents Celeron from beating all overclocking records.
No, no and yes, in that order
This question is marked as answered, but I'd like to add some more information about cache:
Given the same core, more L2 cache typically improves performance between two otherwise like processors depending upon what software is run. For example, if you are running software that is optimized to the smallest cache size, then adding more cache won't improve performance much. But, if the software happens to fit in the larger cache and not in the smaller cache then you'd see big performance improvements.
If you are comparing different cores, especially from different CPU manufacturers, then this is not necessarily so. Cache differences include coherency protocol (keeping all the cache in sync with each other and memory) and (I can't think of the technical term at the moment) whether the cache is mirrored in the next level up or unique to the cache level. _ Cache definitely makes the computer faster, though. Processors perform significantly slower without cache.
There is another side of cache mentioned in the answer: Cache costs the CPU manufacturer money: The bigger cache, the more silicon surface area, the bigger the die, the lower the yield, the more the silicon costs to produce.